English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Face sketch synthesis has been widely used in multi-media entertainment andlaw enforcement. Despite the recent developments in deep neural networks,accurate and realistic face sketch synthesis is still a challenging task due tothe diversity and complexity of human faces. Current image-to-imagetranslation-based face sketch synthesis frequently encounters over-fittingproblems when it comes to small-scale datasets. To tackle this problem, wepresent an end-to-end Memory Oriented Style Transfer Network (MOST-Net) forface sketch synthesis which can produce high-fidelity sketches with limiteddata. Specifically, an external self-supervised dynamic memory module isintroduced to capture the domain alignment knowledge in the long term. In thisway, our proposed model could obtain the domain-transfer ability byestablishing the durable relationship between faces and corresponding sketcheson the feature level. Furthermore, we design a novel Memory Refinement Loss (MRLoss) for feature alignment in the memory module, which enhances the accuracyof memory slots in an unsupervised manner. Extensive experiments on the CUFSand the CUFSF datasets show that our MOST-Net achieves state-of-the-artperformance, especially in terms of the Structural Similarity Index(SSIM).

MOST-Net: A Memory Oriented Style Transfer Network for Face Sketch Synthesis